INDEX

Explanations

code prefixes

The neuron fires on the specific token “f_,” i.e. occurrences of the letter f immediately followed by an underscore.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

-2.23

↵↵

-2.08

-1.87

-1.85

-1.75

 bolsillos

-1.66

 bedrag

-1.57

-1.56

 tremendous

-1.56

-1.55

POSITIVE LOGITS

}");

1.80

 ของ

1.77

 fué

1.75

チール

1.72

Of

1.66

Scopri

1.65

錞

1.63

to

1.63

besondere

1.61

Ingredienti

1.61

Activations Density 0.000%